English
Related papers

Related papers: SuperFlow: Training Flow Matching Models with RL o…

200 papers

Generative models have gained more and more attention in recent years for their remarkable success in tasks that required estimating and sampling data distribution to generate high-fidelity synthetic data. In speech, text-to-speech…

Audio and Speech Processing · Electrical Eng. & Systems 2024-03-27 Alexander H. Liu , Matt Le , Apoorv Vyas , Bowen Shi , Andros Tjandra , Wei-Ning Hsu

Finding effective prompts for language models (LMs) is critical yet notoriously difficult: the prompt space is combinatorially large, rewards are sparse due to expensive target-LM evaluation. Yet, existing RL-based prompt optimizers often…

Artificial Intelligence · Computer Science 2026-02-04 Junmo Cho , Suhan Kim , Sangjune An , Minsu Kim , Dong Bok Lee , Heejun Lee , Sung Ju Hwang , Hae Beom Lee

Diffusion and flow-matching have emerged as powerful methodologies for generative modeling, with remarkable success in capturing complex data distributions and enabling flexible guidance at inference time. Many downstream applications,…

Machine Learning · Computer Science 2026-04-28 Zeyang Li , Kaveh Alim , Navid Azizan

Reinforcement learning is able to solve complex sequential decision-making tasks but is currently limited by sample efficiency and required computation. To improve sample efficiency, recent work focuses on model-based RL which interleaves…

Machine Learning · Computer Science 2023-06-19 Yi Zhao , Wenshuai Zhao , Rinu Boney , Juho Kannala , Joni Pajarinen

Supervised fine-tuning (SFT) is a common method to enhance the tool calling capabilities of Large Language Models (LLMs), with the training data often being synthesized. The current data synthesis process generally involves sampling a set…

Computation and Language · Computer Science 2025-03-18 Zezhong Wang , Xingshan Zeng , Weiwen Liu , Liangyou Li , Yasheng Wang , Lifeng Shang , Xin Jiang , Qun Liu , Kam-Fai Wong

Current Reinforcement Fine-tuning (RFT) paradigms for Large Language Models (LLMs) suffer from sample inefficiency due to the redundant exposure of identical queries under uniform data sampling. While previous work has explored curriculum…

Machine Learning · Computer Science 2025-09-30 Qinsi Wang , Jinghan Ke , Hancheng Ye , Yueqian Lin , Yuzhe Fu , Jianyi Zhang , Kurt Keutzer , Chenfeng Xu , Yiran Chen

Large language models perform well in short text generation but still struggle with long text generation, particularly under complex constraints. Such tasks involve multiple tightly coupled objectives, including global structural…

Computation and Language · Computer Science 2026-03-06 Yifan Zhu , Guanting Chen , Bing Wei , Haoran Luo

Flow matching has emerged as a promising generative approach that addresses the lengthy sampling times associated with state-of-the-art diffusion models and enables a more flexible trajectory design, while maintaining high-quality image…

Computer Vision and Pattern Recognition · Computer Science 2025-11-27 Arnela Hadzic , Franz Thaler , Lea Bogensperger , Simon Johannes Joham , Martin Urschler

Existing rectified flow models are based on linear trajectories between data and noise distributions. This linearity enforces zero curvature, which can inadvertently force the image generation process through low-probability regions of the…

Computer Vision and Pattern Recognition · Computer Science 2025-08-26 Yan Luo , Drake Du , Hao Huang , Yi Fang , Mengyu Wang

Process Reinforcement Learning~(PRL) has demonstrated considerable potential in enhancing the reasoning capabilities of Large Language Models~(LLMs). However, introducing additional process reward models incurs substantial computational…

Machine Learning · Computer Science 2025-07-04 Wu Fei , Hao Kong , Shuxian Liang , Yang Lin , Yibo Yang , Jing Tang , Lei Chen , Xiansheng Hua

Group relative policy optimization (GRPO) has demonstrated significant potential in improving the reasoning capabilities of large language models (LLMs) via reinforcement learning. However, its practical deployment is impeded by an…

Machine Learning · Computer Science 2025-09-29 Yizhou Zhang , Ning Lv , Teng Wang , Jisheng Dang

Recent advancements in reinforcement learning (RL) have achieved great success in fine-tuning diffusion-based generative models. However, fine-tuning continuous flow-based generative models to align with arbitrary user-defined reward…

Machine Learning · Computer Science 2025-02-11 Jiajun Fan , Shuaike Shen , Chaoran Cheng , Yuxin Chen , Chumeng Liang , Ge Liu

In this paper, we propose a unified method to jointly learn optical flow and stereo matching. Our first intuition is stereo matching can be modeled as a special case of optical flow, and we can leverage 3D geometry behind stereoscopic…

Computer Vision and Pattern Recognition · Computer Science 2020-04-07 Pengpeng Liu , Irwin King , Michael Lyu , Jia Xu

This paper studies the training-testing discrepancy (a.k.a. exposure bias) problem for improving the diffusion models. During training, the input of a prediction network at one training timestep is the corresponding ground-truth noisy data…

Computer Vision and Pattern Recognition · Computer Science 2025-12-23 Hui Li , Jiayue Lyu , Fu-Yun Wang , Kaihui Cheng , Siyu Zhu , Jingdong Wang

Adapting large language models (LLMs) via reinforcement learning (RL) is often bottlenecked by the generation stage, which can consume over 75\% of the training time. Speculative decoding (SD) accelerates autoregressive generation in…

Machine Learning · Computer Science 2025-10-31 Qiaoling Chen , Zijun Liu , Peng Sun , Shenggui Li , Guoteng Wang , Ziming Liu , Yonggang Wen , Siyuan Feng , Tianwei Zhang

Recent reinforcement learning (RL) techniques have yielded impressive reasoning improvements in language models, yet it remains unclear whether post-training truly extends a model's reasoning ability beyond what it acquires during…

Computation and Language · Computer Science 2025-12-09 Charlie Zhang , Graham Neubig , Xiang Yue

Rectified Flow offers a simple and effective approach to high-quality generative modeling by learning a velocity field. However, we identify a limitation in directly modeling the velocity with an unconstrained neural network: the learned…

Machine Learning · Computer Science 2025-10-21 Xixi Hu , Runlong Liao , Keyang Xu , Bo Liu , Yeqing Li , Eugene Ie , Hongliang Fei , Qiang Liu

Flow-based super-resolution (SR) models have demonstrated astonishing capabilities in generating high-quality images. However, these methods encounter several challenges during image generation, such as grid artifacts, exploding inverses,…

Computer Vision and Pattern Recognition · Computer Science 2024-05-30 Li-Yuan Tsao , Yi-Chen Lo , Chia-Che Chang , Hao-Wei Chen , Roy Tseng , Chien Feng , Chun-Yi Lee

Normalizing flows are a class of probabilistic generative models which allow for both fast density computation and efficient sampling and are effective at modelling complex distributions like images. A drawback among current methods is…

Computer Vision and Pattern Recognition · Computer Science 2020-10-28 Jason J. Yu , Konstantinos G. Derpanis , Marcus A. Brubaker

Large Language Models (LLMs) have demonstrated profound impact on Natural Language Processing (NLP) tasks. However, their effective deployment across diverse domains often require domain-specific adaptation strategies, as generic models may…

Artificial Intelligence · Computer Science 2025-10-15 Jingyi Wang , Hongyuan Zhu , Ye Niu , Yunhui Deng